位置：成果数据库 > 会议 > 会议详情页
Source-to-Source Vectorization for OpenCL Kernels
  • 所属机构名称：中国人民解放军国防科学技术大学
  • 会议名称：2012 16th Workshop on Compilers for Parallel Computing
  • 时间：2012.1.11
  • 成果类型：会议
  • 相关项目：基于多面体模型的迭代编译优化方法研究
作者： Jianbin Fang|Ana Lucia Varbanescu|Alexander S|van Amesfoort|Henk J. Sips|
同会议论文项目
基于多面体模型的迭代编译优化方法研究
期刊论文 9 会议论文 16
同项目会议论文
Hardware Acceleration of Barrier Communication for Large Scale Parallel Computer
Scalable NIC Architecture to Support Offloading of Large Scale MPI
一种基于改进模拟退火算法的程序性能优化参数搜索算法
Quantifying the performance impacts of using local memory for many-core processors
Combining program analysis and empirical search to optimize programs
Test-Driving Intel Xeon Phi
ELMO: A User-Friendly API to Enable Local Memory in OpenCL Kernels
The evaluation and optimization of 3-D Jacobi iteration on a stream processor
Accelerating Cost Aggregation for Real-Time Stereo Matching
Mapping and optimizing 2-D scientific applications on a stream
An effective framework of program optimization for high performance computing
Sesame: A User-Transparent Optimizing Framework for Many-Core Processors
Grover: Looking for Performance Improvement by Disabling Local Memory Usage in OpenCL Kernels
Identifying the Key Features of Intel Xeon Phi
ILGA: an improved local greedy algorithm for optimization parameters searches